A prediction model and web-based prediction score calculator for comorbidity of psoriasis and psoriatic arthritis

Abstract

The present invention relates to a prediction model for the comorbidity of psoriasis and psoriatic arthritis, and the prediction model is constructed by the following methods: S1 data collection and preprocessing: S11 collects data of psoriasis patients; S12 supplements and preprocesses missing data; S2 variable selection: S21 uses the least absolute shrinkage and selection operator regression method to screen key variables; S22 selects important predictive variables; S3 model construction: S31 uses a multifactor logistic regression model for modeling; S32 optimizes model parameters through 10-fold cross validation during model construction; S4 model evaluation: S41 uses the area under the receiver operating characteristic curve to evaluate the prediction performance of the model; S42 uses the Hosmer-Lemeshow test to evaluate the calibration of the model; S43 verifies the net effect of the model through decision curve analysis and clinical impact curve. The present invention also provides a prediction webpage version prediction score calculator. The prediction results and analysis reports provided by the system of the present invention provide support for clinical decision-making and patient management, and improve medical quality.

Description

Technical Field

[0001] The present invention relates to the field of medical treatment and health management, and in particular to a prediction model and a web-based prediction score calculator for the comorbidity of psoriasis and psoriatic arthritis. Background Art

[0002] Psoriasis is a chronic, inflammatory skin disease characterized by red, scaly patches on the skin. In recent years, studies have shown that people with psoriasis have a significantly increased risk of developing psoriatic arthritis (PsA), an inflammatory arthritis that affects the joints and can cause joint pain, stiffness, and dysfunction.

[0003] Although there are currently a variety of clinical methods for diagnosing PsA, these methods usually rely on the doctor's experience and subjective judgment, and lack unified standards and early prediction tools. This leads to difficulties in early identification and intervention of high-risk patients in clinical practice, which in turn affects the treatment effect and quality of life of patients. Therefore, it is of great clinical significance to develop a prediction model based on big data and machine learning to assess the risk of PsA comorbidity in patients with psoriasis.

[0004] In existing research and practice, some success has been achieved in developing prediction models using big data and machine learning techniques, such as in the fields of diabetes and cardiovascular disease. However, prediction models for the risk of comorbidity of psoriasis and PsA are still relatively lacking. Therefore, the present invention aims to fill this gap by collecting and analyzing a large amount of clinical data to build an efficient and accurate prediction model to help clinicians identify high-risk patients early, so as to take timely intervention measures and improve patient prognosis.

[0005] Chinese patent document CN116313106A discloses a method for constructing a prediction model for portal vein thrombosis in patients with liver cirrhosis and a network calculator, comprising the following steps: S1, data collection, obtaining clinical test indicators of the research subjects, and calculating indirect indicators through multiple clinical test indicators; S2, screening of independent prediction features, taking whether portal vein thrombosis occurs as the dependent variable, using the obtained clinical test indicators and indirect indicators to establish a univariate regression model, calculating the correlation between the clinical test indicators and the indirect indicators and the risk of portal vein thrombosis, screening out relevant indicators related to the risk of portal vein thrombosis, performing multivariate logistic regression on the relevant indicators, and screening out independent prediction features of the risk of portal vein thrombosis; S3, construction of the prediction model; S4, generating a network calculator, constructing a portal vein thrombosis prediction nomogram according to the weight coefficients of each prediction feature in the prediction model nomogram, and further generating a network calculator based on the nomogram.

[0006] However, there are currently no reports on prediction models and web-based prediction score calculators for the comorbidity of psoriasis and psoriatic arthritis. Summary of the invention

[0007] The purpose of the present invention is to address the deficiencies in the prior art and provide a prediction model and a web-based prediction score calculator for the comorbidity of psoriasis and psoriatic arthritis. By collecting and analyzing a variety of clinical data of patients, early prediction of the risk of PsA comorbidity in psoriasis patients can be achieved, thereby providing decision support for clinicians, optimizing patient management, and reducing the incidence of PsA comorbidity.

[0008] In a first aspect, the present invention provides

[0009] A prediction model for the comorbidity of psoriasis and psoriatic arthritis, wherein the prediction model for the comorbidity of psoriasis and psoriatic arthritis is constructed by the following method:

[0010] S1 Data collection and preprocessing:

[0011] S11 collects data on patients with psoriasis;

[0012] S12 supplements and preprocesses missing data;

[0013] S2 variable selection:

[0014] S21 uses the least absolute shrinkage and selection operator regression methods to screen key variables;

[0015] S22 Select important predictor variables

[0016] S3 model building:

[0017] S31 was modeled using a multivariate logistic regression model;

[0018] During the model building process, S32 optimized the model parameters through 10-fold cross validation;

[0019] S4 Model Evaluation:

[0020] S41 used the area under the receiver operating characteristic curve to evaluate the predictive performance of the model;

[0021] S42 used the Hosmer-Lemeshow test to assess the calibration of the model;

[0022] S43 The net effectiveness of the model was verified by decision curve analysis and clinical impact curve.

[0023] In a second aspect, the present invention provides

[0024] A web-based prediction score calculator for the prediction of comorbidity of psoriasis and psoriatic arthritis constructed by the following method:

[0025] S1 Data collection and preprocessing:

[0026] S11 collects data on patients with psoriasis;

[0027] S12 supplements and preprocesses missing data;

[0028] S2 variable selection:

[0029] S21 uses the least absolute shrinkage and selection operator regression methods to screen key variables;

[0030] S22 Select important predictor variables

[0031] S3 model building:

[0032] S31 was modeled using a multivariate logistic regression model;

[0033] During the model building process, S32 optimized the model parameters through 10-fold cross validation;

[0034] S4 Model Evaluation:

[0035] S41 used the area under the receiver operating characteristic curve to evaluate the predictive performance of the model;

[0036] S42 used the Hosmer-Lemeshow test to assess the calibration of the model;

[0037] S43 validates the net effectiveness of the model through decision curve analysis and clinical impact curve;

[0038] S5: A web-based calculator where the user can input the patient’s clinical data and the system will calculate the risk score for psoriatic arthritis based on the trained model.

[0039] As a preferred example, the system outputs the risk classification of psoriatic arthritis according to the results of model calculation, which is divided into low risk, medium risk and high risk.

[0040] As another preferred example, a visual interface is also included: an input box is used to fill in the patient's key variable data, and the psoriatic arthritis risk score is displayed in a visual form, with additional risk grading prompts.

[0041] The advantages of the present invention are:

[0042] 1. Improve prediction accuracy: Based on big data and advanced machine learning algorithms, it can accurately predict the risk of PsA comorbidity in psoriasis patients and identify high-risk patients.

[0043] 2. Early intervention: By identifying high-risk patients early, clinicians can take timely intervention measures to reduce the incidence of PsA and improve patients' quality of life.

[0044] 3. Optimized management: The prediction results and analysis reports provided by the system provide strong support for clinical decision-making and patient management, and improve the quality of medical services. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 Flowchart of the prediction model and web-based prediction score calculator for comorbidity of psoriasis and psoriatic arthritis. DETAILED DESCRIPTION

[0046] The present invention will be further described below in conjunction with specific embodiments. It should be understood that these embodiments are only used to illustrate the present invention and are not intended to limit the scope of the present invention. In addition, it should be understood that after reading the content of the present invention, those skilled in the art can make various changes or modifications to the present invention, and these equivalent forms fall within the scope limited by the appended claims of the application equally.

[0047] Example 1

[0048] 1. Data collection and preprocessing:

[0049] Data on psoriasis patients were collected from 49 hospitals across the country, including multiple health-related factors such as gender, age, BMI, and medical history.

[0050] Missing data were supplemented and preprocessed to ensure the completeness and accuracy of the data.

[0051] 2. Variable selection:

[0052] The least absolute shrinkage and selection operator (LASSO) regression method is used to screen key variables. LASSO regression reduces the weight of unimportant variables by introducing regularization terms, thereby achieving variable selection and model simplification.

[0053] Finally, several important predictor variables are selected, which have high predictive value in the model.

[0054] 3. Model construction:

[0055] A multivariate logistic regression model was used for modeling. Multivariate logistic regression is suitable for dealing with binary classification problems and can predict the risk of psoriatic arthritis in patients with psoriasis.

[0056] During the model building process, 10-fold cross validation was used to optimize the model parameters to improve the stability and generalization ability of the model.

[0057] 4. Model Evaluation:

[0058] The area under the receiver operating characteristic curve (AUC) was used to evaluate the predictive performance of the model. The higher the AUC value, the stronger the discrimination ability of the model.

[0059] The Hosmer-Lemeshow test was used to assess the calibration of the model and ensure the reliability of the prediction results.

[0060] The net benefit and clinical practicality of the model were verified by decision curve analysis (DCA) and clinical impact curve (CIC).

[0061] 5. System implementation:

[0062] Develop a web-based calculator where users can enter their patients’ clinical data and the system will calculate a psoriatic arthritis risk score based on the trained model.

[0063] System Implementation

[0064] 1. Risk Calculator

[0065] Provide a web-based calculator where users input the patient's clinical data (such as age, BMI, PASI score, etc.) and the system calculates in real time the probability of psoriasis patients having comorbid psoriatic arthritis.

[0066] 2. Visual interface

[0067] The input box is used to fill in the patient's key variable data.

[0068] Display the probability of psoriasis patients having comorbid psoriatic arthritis in clear text or simple visualization.

[0069] 3. Technical Implementation

[0070] The system supports online access and automatically calls the trained model for calculation after inputting data.

[0071] All data is encrypted, stored and processed to ensure patient privacy.

[0072] The above is only a preferred embodiment of the present invention. It should be pointed out that ordinary technicians in this technical field can make several improvements and supplements without departing from the method of the present invention. These improvements and supplements should also be regarded as the scope of protection of the present invention.

Claims

1. A prediction model for the comorbidity of psoriasis and psoriatic arthritis, characterized in that: The prediction model for the comorbidity of psoriasis and psoriatic arthritis was constructed by the following method: S1 Data collection and preprocessing: S11 collects data on patients with psoriasis; S12 supplements and preprocesses missing data; S2 variable selection: S21 uses the least absolute shrinkage and selection operator regression methods to screen key variables; S22 Select important predictor variables S3 model building: S31 was modeled using a multivariate logistic regression model; During the model building process, S32 optimized the model parameters through 10-fold cross validation; S4 Model Evaluation: S41 used the area under the receiver operating characteristic curve to evaluate the predictive performance of the model; S42 used the Hosmer-Lemeshow test to assess the calibration of the model; S43 The net effectiveness of the model was verified by decision curve analysis and clinical impact curve.

2. A web-based prediction score calculator for predicting the comorbidity of psoriasis and psoriatic arthritis, characterized by: Constructed by: S1 Data collection and preprocessing: S11 collects data on patients with psoriasis; S12 supplements and preprocesses missing data; S2 variable selection: S21 uses the least absolute shrinkage and selection operator regression methods to screen key variables; S22 Select important predictor variables S3 model building: S31 was modeled using a multivariate logistic regression model; During the model building process, S32 optimized the model parameters through 10-fold cross validation; S4 Model Evaluation: S41 used the area under the receiver operating characteristic curve to evaluate the predictive performance of the model; S42 used the Hosmer-Lemeshow test to assess the calibration of the model; S43 validates the net effectiveness of the model through decision curve analysis and clinical impact curve; S5: A web-based calculator where the user can input the patient’s clinical data and the system will calculate the risk score for psoriatic arthritis based on the trained model.

3. The web-based prediction score calculator for predicting the comorbidity of psoriasis and psoriatic arthritis according to claim 2, characterized in that: The system outputs the risk classification of psoriatic arthritis based on the results of model calculation, which is divided into low risk, medium risk and high risk.

4. The web-based prediction score calculator for predicting the comorbidity of psoriasis and psoriatic arthritis according to claim 2, characterized in that: It also includes a visual interface: an input box is used to fill in the patient's key variable data, and the psoriatic arthritis risk score is displayed in a visual form with additional risk grading prompts.

Images